Sense discrimination with parallel corpora

Ide, Nancy; Erjavec, Tomaž; Tufiș, Dan

doi:10.3115/1118675.1118683

Cited by 48 publications

(30 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…[16,17]), as well as on parallel corpora. Previous research on parallel corpora [18,7] confirmed the use of cross-lingual lexicalization as a criterion for performing sense discrimination. Whereas in previous research on cross-lingual WSD the evidence from the aligned sentences was mainly used to enrich WordNet information, our approach does not require any external resources.…”

Section: Feature Vectorsmentioning

confidence: 83%

“…Using a parallel corpus, such as for example Europarl, instead of human defined sense-labels offers some advantages: (1) for most languages we do not have large sense-annotated corpora or sense inventories, (2) using corpus translations should make it easier to integrate the WSD module into real multilingual applications and (3) this approach implicitly deals with the granularity problem, as fine sense distinctions (that are often listed in electronic sense inventories) are only relevant in case they get lexicalized in the target translations. The idea to use translations from parallel corpora to distinguish between word senses is based on the hypothesis that different meanings of a polysemous word are lexicalized across languages [6,7]. Many WSD studies have already shown the validity of this cross-lingual evidence idea.…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

Examining the Validity of Cross-Lingual Word Sense Disambiguation

Lefever¹,

Hoste²

2011

Polibits

View full text Add to dashboard Cite

Abstract. This paper describes a set of experiments in which the viability of a classification-based Word Sense Disambiguation system that uses evidence from multiple languages is investigated. Instead of using a predefined monolingual sense-inventory such as WordNet, we use a language-independent framework and start from a manually constructed gold standard in which the word senses are made up by the translations that result from word alignments on a parallel corpus. To train and test the classifier, we used English as an input language and we incorporated the translations of our target words in five languages (viz. Spanish, Italian, French, Dutch and German) as features in the feature vectors. Our results show that the multilingual approach outperforms the classification experiments where no additional evidence from other languages is used. These results confirm our initial hypothesis that each language adds evidence to further refine the senses of a given word. This allows us to develop a proof of concept for a multilingual approach to Word Sense Disambiguation.

show abstract

Section: Feature Vectorsmentioning

confidence: 83%

Section: Introductionmentioning

confidence: 99%

Examining the Validity of Cross-Lingual Word Sense Disambiguation

Lefever¹,

Hoste²

2011

Polibits

View full text Add to dashboard Cite

show abstract

“…One is the use of parallel corpora for unsupervised word sense disambiguation. While parallel texts have been the foundation on which modern statistical machine translation now stands [5,6], their utility extends to semantically related tasks as well, such as inducing bilingual dictionaries [22] and translating collocations [39]. Their use in word sense disambiguation [21] rivals or surpasses other unsupervised methods, and they have been used with success with translation pairs in English/French [13], English/Chinese [8,31], English/Portuguese [40], and English/Vietnamese [14].…”

Section: Related Workmentioning

confidence: 99%

Measuring historical word sense variation

Bamman

Crane

2011

Proceedings of the 11th Annual International ACM/IEEE Joint Conference on Digital Libraries

View full text Add to dashboard Cite

We describe here a method for automatically identifying word sense variation in a dated collection of historical books in a large digital library. By leveraging a small set of known translation book pairs to induce a bilingual sense inventory and labeled training data for a WSD classifier, we are able to automatically classify the Latin word senses in a 389 million word corpus and track the rise and fall of those senses over a span of two thousand years. We evaluate the performance of seven different classifiers both in a tenfold test on 83,892 words from the aligned parallel corpus and on a smaller, manually annotated sample of 525 words, measuring both the overall accuracy of each system and how well that accuracy correlates (via mean square error) to the observed historical variation.

show abstract

“…In more recent years, Ide et al (2002) present a method to identify word meanings starting from a multilingual corpus. A by-product of applying this method is that once a word in one language is word-sense tagged, the translation equivalents in the parallel texts are also automatically annotated.…”

Section: Related Workmentioning

confidence: 99%

Evaluating cross-language annotation transfer in the MultiSemCor corpus

Bentivogli¹,

Forner²,

Pianta³

2004

Proceedings of the 20th International Conference on Computational Linguistics - COLING '04

View full text Add to dashboard Cite

In this paper we illustrate and evaluate an approach to the creation of high quality linguistically annotated resources based on the exploitation of aligned parallel corpora. This approach is based on the assumption that if a text in one language has been annotated and its translation has not, annotations can be transferred from the source text to the target using word alignment as a bridge. The transfer approach has been tested in the creation of the MultiSemCor corpus, an English/Italian parallel corpus created on the basis of the English SemCor corpus. In MultiSemCor texts are aligned at the word level and semantically annotated with a shared inventory of senses. We present some experiments carried out to evaluate the different steps involved in the methodology. The results of the evaluation suggest that the cross-language annotation transfer methodology is a promising solution allowing for the exploitation of existing (mostly English) annotated resources to bootstrap the creation of annotated corpora in new (resourcepoor) languages with greatly reduced human effort.

show abstract

Sense discrimination with parallel corpora

Cited by 48 publications

References 9 publications

Examining the Validity of Cross-Lingual Word Sense Disambiguation

Examining the Validity of Cross-Lingual Word Sense Disambiguation

Measuring historical word sense variation

Evaluating cross-language annotation transfer in the MultiSemCor corpus

Contact Info

Product

Resources

About